Ed Wios
It'd be great if it works on Mac. What is needed to have it supported on Mac OSX?
Same problem here, any idea who is the party to blame? A1111's extension mechanism or the extensions? It looks like to me that somewhere in the A1111's code (maybe `script.before_process()`...
We should _not_ encourage this kind of unsafe practice, and it is hard to imagine any web site still doesn't have a properly signed cert given there is LetsEncrypt and...
Something's not quite right here. It took my M1 Max 64GB RAM exactly 4 hours to convert the `base.en` and almost 3 hours to convert the medium.en (which didn't load...
Yes, the link @ggerganov gave above works. Just use the same `tokenizer.model` that comes with the LLaMA models. Download the script mentioned in the link above, save it as, for...
Use this script `convert-unversioned-ggml-to-ggml.py` that comes with the llama.cpp. For example: `python convert-unversioned-ggml-to-ggml.py models/13B/oldggml/ggml-model-q4_0.bin models/13B/ggml-model-q4_0.bin`
> > Use this script `convert-unversioned-ggml-to-ggml.py` that comes with the llama.cpp. > > For example: > > `python convert-unversioned-ggml-to-ggml.py models/13B/oldggml/ggml-model-q4_0.bin models/13B/ggml-model-q4_0.bin` > > And just to confirm, the file that...
> RuntimeError: The size of tensor a (4) must match the size of tensor b (9) at non-singleton dimension 1 Affirmative, this only occurs with the sd.15-inpaint with _any_ controlnet...
Latest commit b6b268d4415fd3b3e53f22b6619b724d4928f713 gives segmentation fault right away without even dropping into the input prompt. Was run on a Mac M1 Max with 64GB RAM. The crash happened on 30B...
Last known good commit I have just tested was indeed 404e1da38ec8025707031a8027da14dc1590f952